SIGFinger: A subtle and interactive GNN fingerprinting scheme via spatial structure inference perturbation
Publication Type
Journal Article
Publication Date
7-2025
Abstract
There have been significant improvements in intellectual property (IP) protection for deep learning models trained on euclidean data. However, the complex and irregular graph-structured data in non-euclidean space poses a huge challenge to the IP protection of graph neural networks (GNNs). To address this issue, we propose a subtle and interactive GNN fingerprinting scheme through spatial structure inference perturbation, which captures the stable coordination patterns of fingerprint to guarantee the reliability of copyright verification. Specifically, the data augmentation based on adaptive graph diffusion is first exploited to generate more samples, which enables the exploration of fingerprint information from coarse to fine. Subsequently, the graph-structured data are manipulated by multi-constrained spectral clustering to analyze intrinsic and extrinsic structure correlations in a causal inference manner. Ultimately, the cycle-consistent statistical optimization is performed to determine the copyright of GNN models from both intra-graph and inter-graph perspectives. Extensive experiments show that our proposed scheme can effectively verify the IP of GNN models on various challenging graph-structured datasets. Furthermore, we reveal that the space causality inference can facilitate the acquisition of inherent structural information, which improves the quality and robustness of the fingerprint under model modification operations and other model stealing attacks.
Keywords
IP protection, GNN fingerprinting, causal inference, stable structure knowledge, quality and robustness.
Discipline
Information Security
Research Areas
Information Systems and Management
Publication
IEEE Transactions on Dependable and Secure Computing
Volume
22
Issue
4
First Page
3629
Last Page
3646
ISSN
1545-5971
Identifier
10.1109/TDSC.2025.3535588
Publisher
Institute of Electrical and Electronics Engineers
Citation
JIA, Ju; LI, Renjie; WU, Cong; MA, Siqi; WANG, Lina; and DENG, Robert H..
SIGFinger: A subtle and interactive GNN fingerprinting scheme via spatial structure inference perturbation. (2025). IEEE Transactions on Dependable and Secure Computing. 22, (4), 3629-3646.
Available at: https://ink.library.smu.edu.sg/sis_research/10443
Additional URL
https://doi.org/10.1109/TDSC.2025.3535588